Robust Semi-Supervised Anomaly Detection via Adversarially Learned Continuous Noise Corruption (2023)
Conference Proceeding
Barker, J., Bhowmik, N., Gaus, Y., & Breckon, T. (2023). Robust Semi-Supervised Anomaly Detection via Adversarially Learned Continuous Noise Corruption. . https://doi.org/10.5220/0011684700003417

Anomaly detection is the task of recognising novel samples which deviate significantly from pre-established normality. Abnormal classes are not present during training meaning that models must learn effective representations solely across normal clas... Read More about Robust Semi-Supervised Anomaly Detection via Adversarially Learned Continuous Noise Corruption.

ACR: Attention Collaboration-based Regressor for Arbitrary Two-Hand Reconstruction (2023)
Conference Proceeding
Yu, Z., Haung, S., Fang, C., Breckon, T., & Wang, J. (2023). ACR: Attention Collaboration-based Regressor for Arbitrary Two-Hand Reconstruction. In 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). https://doi.org/10.1109/CVPR52729.2023.01245

Reconstructing two hands from monocular RGB images is challenging due to frequent occlusion and mutual confusion. Existing methods mainly learn an entangled representation to encode two interacting hands, which are incredibly fragile to impaired inte... Read More about ACR: Attention Collaboration-based Regressor for Arbitrary Two-Hand Reconstruction.

Less is More: Reducing Task and Model Complexity for 3D Point Cloud Semantic Segmentation (2023)
Conference Proceeding
Li, L., Shum, H. P., & Breckon, T. P. (2023). Less is More: Reducing Task and Model Complexity for 3D Point Cloud Semantic Segmentation. In 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). https://doi.org/10.1109/CVPR52729.2023.00903

Whilst the availability of 3D LiDAR point cloud data has significantly grown in recent years, annotation remains expensive and time-consuming, leading to a demand for semisupervised semantic segmentation methods with application domains such as auton... Read More about Less is More: Reducing Task and Model Complexity for 3D Point Cloud Semantic Segmentation.

Seeing Through the Data: A Statistical Evaluation of Prohibited Item Detection Benchmark Datasets for X-ray Security Screening (2023)
Conference Proceeding
Issac-Medina, B., Yucer, S., Bhowmik, N., & Breckon, T. (2023). Seeing Through the Data: A Statistical Evaluation of Prohibited Item Detection Benchmark Datasets for X-ray Security Screening. In 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW). https://doi.org/10.1109/CVPRW59228.2023.00059

The rapid progress in automatic prohibited object detection within the context of X-ray security screening, driven forward by advances in deep learning, has resulted in the first internationally-recognized, application-focused object detection perfor... Read More about Seeing Through the Data: A Statistical Evaluation of Prohibited Item Detection Benchmark Datasets for X-ray Security Screening.

Region-based Appearance and Flow Characteristics for Anomaly Detection in Infrared Surveillance Imagery (2023)
Conference Proceeding
Gaus, Y., Bhowmik, N., Issac-Medina, B., Atapour-Abarghouei, A., Shum, H., & Breckon, T. (2023). Region-based Appearance and Flow Characteristics for Anomaly Detection in Infrared Surveillance Imagery. In 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW). https://doi.org/10.1109/CVPRW59228.2023.00301

Anomaly detection is a classical problem within automated visual surveillance, namely the determination of the normal from the abnormal when operational data availability is highly biased towards one class (normal) due to both insufficient sample siz... Read More about Region-based Appearance and Flow Characteristics for Anomaly Detection in Infrared Surveillance Imagery.

On Fine-tuned Deep Features for Unsupervised Domain Adaptation (2023)
Conference Proceeding
Wang, Q., Meng, F., & Breckon, T. (2023). On Fine-tuned Deep Features for Unsupervised Domain Adaptation. . https://doi.org/10.1109/IJCNN54540.2023.10191262

Prior feature transformation based approaches to Unsupervised Domain Adaptation (UDA) employ the deep features extracted by pre-trained deep models without fine-tuning them on the specific source or target domain data for a particular domain adaptati... Read More about On Fine-tuned Deep Features for Unsupervised Domain Adaptation.

Exact-NeRF: An Exploration of a Precise Volumetric Parameterization for Neural Radiance Fields (2023)
Conference Proceeding
Isaac-Medina, B., Willcocks, C., & Breckon, T. (2023). Exact-NeRF: An Exploration of a Precise Volumetric Parameterization for Neural Radiance Fields.

Neural Radiance Fields (NeRF) have attracted significant attention due to their ability to synthesize novel scene views with great accuracy. However, inherent to their underlying formulation, the sampling of points along a ray with zero width may res... Read More about Exact-NeRF: An Exploration of a Precise Volumetric Parameterization for Neural Radiance Fields.

Generalized Zero-Shot Domain Adaptation via Coupled Conditional Variational Autoencoders (2023)
Journal Article
Wang, Q., & Breckon, T. (2023). Generalized Zero-Shot Domain Adaptation via Coupled Conditional Variational Autoencoders. Neural Networks, 163, 40-52. https://doi.org/10.1016/j.neunet.2023.03.033

Domain adaptation aims to exploit useful information from the source domain where annotated training data are easier to obtain to address a learning problem in the target domain where only limited or even no annotated data are available. In classific... Read More about Generalized Zero-Shot Domain Adaptation via Coupled Conditional Variational Autoencoders.

Data Augmentation with norm-VAE and Selective Pseudo-Labelling for Unsupervised Domain Adaptation (2023)
Journal Article
Wang, Q., Meng, F., & Breckon, T. (2023). Data Augmentation with norm-VAE and Selective Pseudo-Labelling for Unsupervised Domain Adaptation. Neural Networks, 161, 614-625. https://doi.org/10.1016/j.neunet.2023.02.006

We address the Unsupervised Domain Adaptation (UDA) problem in image classification from a new perspective. In contrast to most existing works which either align the data distributions or learn domain-invariant features, we directly learn a unified c... Read More about Data Augmentation with norm-VAE and Selective Pseudo-Labelling for Unsupervised Domain Adaptation.

Joint Sub-component Level Segmentation and Classification for Anomaly Detection within Dual-Energy X-Ray Security Imagery (2022)
Conference Proceeding
Bhowmik, N., & Breckon, T. (2022). Joint Sub-component Level Segmentation and Classification for Anomaly Detection within Dual-Energy X-Ray Security Imagery.

X-ray baggage security screening is in widespread use and crucial to maintaining transport security for threat/anomaly detection tasks. The automatic detection of anomaly, which is concealed within cluttered and complex electronics/electrical items,... Read More about Joint Sub-component Level Segmentation and Classification for Anomaly Detection within Dual-Energy X-Ray Security Imagery.

UAV-ReID: A Benchmark on Unmanned Aerial Vehicle Re-Identification in Video Imagery (2022)
Conference Proceeding
Organisciak, D., Poyser, M., Alsehaim, A., Hu, S., Isaac-Medina, B. K., Breckon, T. P., & Shum, H. P. (2022). UAV-ReID: A Benchmark on Unmanned Aerial Vehicle Re-Identification in Video Imagery. . https://doi.org/10.5220/0010836600003124

As unmanned aerial vehicles (UAV) become more accessible with a growing range of applications, the risk of UAV disruption increases. Recent development in deep learning allows vision-based counter-UAV systems to detect and track UAVs with a single ca... Read More about UAV-ReID: A Benchmark on Unmanned Aerial Vehicle Re-Identification in Video Imagery.

Crowd Counting via Segmentation Guided Attention Networks and Curriculum Loss (2022)
Journal Article
Wang, Q., & Breckon, T. (2022). Crowd Counting via Segmentation Guided Attention Networks and Curriculum Loss. IEEE Transactions on Intelligent Transportation Systems, https://doi.org/10.1109/tits.2021.3138896

Automatic crowd behaviour analysis is an important task for intelligent transportation systems to enable effective flow control and dynamic route planning for varying road participants. Crowd counting is one of the keys to automatic crowd behaviour a... Read More about Crowd Counting via Segmentation Guided Attention Networks and Curriculum Loss.

VID-Trans-ReID: Enhanced Video Transformers for Person Re-identification (2022)
Conference Proceeding
Alsehaim, A., & Breckon, T. (2022). VID-Trans-ReID: Enhanced Video Transformers for Person Re-identification.

Video-based person Re-identification (Re-ID) has received increasing attention recently due to its important role within surveillance video analysis. Video-based Re- ID expands upon earlier image-based methods by extracting person features temporally... Read More about VID-Trans-ReID: Enhanced Video Transformers for Person Re-identification.

Does lossy image compression affect racial bias within face recognition? (2022)
Conference Proceeding
Yucer, S., Poyser, M., Al Moubayed, N., & Breckon, T. (2022). Does lossy image compression affect racial bias within face recognition?.

This study investigates the impact of commonplace lossy image compression on face recognition algorithms with regard to the racial characteristics of the subject. We adopt a recently proposed racial phenotype-based bias analysis methodology to measur... Read More about Does lossy image compression affect racial bias within face recognition?.

Unleashing Transformers: Parallel Token Prediction with Discrete Absorbing Diffusion for Fast High-Resolution Image Generation from Vector-Quantized Codes (2022)
Conference Proceeding
Bond-Taylor, S., Hessey, P., Sasaki, H., Breckon, T., & Willcocks, C. (2022). Unleashing Transformers: Parallel Token Prediction with Discrete Absorbing Diffusion for Fast High-Resolution Image Generation from Vector-Quantized Codes. In ECCV 2022: Computer Vision – ECCV 2022 (170-188)

Whilst diffusion probabilistic models can generate high quality image content, key limitations remain in terms of both generating high-resolution imagery and their associated high computational requirements. Recent Vector-Quantized image models have... Read More about Unleashing Transformers: Parallel Token Prediction with Discrete Absorbing Diffusion for Fast High-Resolution Image Generation from Vector-Quantized Codes.

On Depth Error from Spherical Camera Calibration within Omnidirectional Stereo Vision (2022)
Conference Proceeding
Groom, M., & Breckon, T. (2022). On Depth Error from Spherical Camera Calibration within Omnidirectional Stereo Vision.

As a depth sensing approach, whilst stereo vision provides a good compromise between accuracy and cost, a key limitation is the limited field of view of the conventional cameras that are used within most stereo configurations. By contrast, the use of... Read More about On Depth Error from Spherical Camera Calibration within Omnidirectional Stereo Vision.

Multi-view Vision Transformers for Object Detection (2022)
Conference Proceeding
Isaac-Medina, B., Willcocks, C., & Breckon, T. (2022). Multi-view Vision Transformers for Object Detection.

Evaluating Gaussian Grasp Maps for Generative Grasping Models (2022)
Conference Proceeding
Prew, W., Breckon, T., Bordewich, M., & Beierholm, U. (2022). Evaluating Gaussian Grasp Maps for Generative Grasping Models.

Generalising robotic grasping to previously unseen objects is a key task in general robotic manipulation. The current method for training many antipodal generative grasping models rely on a binary ground truth grasp map generated from the centre thir... Read More about Evaluating Gaussian Grasp Maps for Generative Grasping Models.

Lost in Compression: the Impact of Lossy Image Compression on Variable Size Object Detection within Infrared Imagery (2022)
Conference Proceeding
Bhowmik, N., Barker, J., Gaus, Y., & Breckon, T. (2022). Lost in Compression: the Impact of Lossy Image Compression on Variable Size Object Detection within Infrared Imagery. . https://doi.org/10.1109/cvprw56347.2022.00052

Lossy image compression strategies allow for more efficient storage and transmission of data by encoding data to a reduced form. This is essential enable training with larger datasets on less storage-equipped environments. However, such compression c... Read More about Lost in Compression: the Impact of Lossy Image Compression on Variable Size Object Detection within Infrared Imagery.

Cross-modal Image Synthesis in Dual-Energy X-Ray Security Imagery (2022)
Conference Proceeding
Isaac-Medina, B., Bhowmik, N., Willcocks, C., & Breckon, T. (2022). Cross-modal Image Synthesis in Dual-Energy X-Ray Security Imagery. . https://doi.org/10.1109/cvprw56347.2022.00048

Dual-energy X-ray scanners are used for aviation security screening given their capability to discriminate materials inside passenger baggage. To facilitate manual operator inspection, a pseudo-colouring is assigned to the effective composition of th... Read More about Cross-modal Image Synthesis in Dual-Energy X-Ray Security Imagery.